Efficient pose estimation using view-based object representations

Authors:
Gabriele Peters
Affiliations:
Universität Dortmund, Informatik VII, Dortmund, Germany
Venue:
ICVS'03 Proceedings of the 3rd international conference on Computer vision systems
Year:
2003

Citing 6
Cited 0

Three-dimensional object recognition from single two-dimensional images

Artificial Intelligence
An analytic solution for the perspective 4-point problem

Computer Vision, Graphics, and Image Processing
Determination of the Attitude of 3D Objects from a Single Perspective View

IEEE Transactions on Pattern Analysis and Machine Intelligence
Recognition by Linear Combinations of Models

IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part I
Distortion Invariant Object Recognition in the Dynamic Link Architecture

IEEE Transactions on Computers
Tracking and Learning Graphs and Pose on Image Sequences of Faces

FG '96 Proceedings of the 2nd International Conference on Automatic Face and Gesture Recognition (FG '96)

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present an efficient method for estimating the pose of a three-dimensional object. Its implementation is embedded in a computer vision system which is motivated by and based on cognitive principles concerning the visual perception of three-dimensional objects. Viewpoint-invariant object recognition has been subject to controversial discussions for a long time. An important point of discussion is the nature of internal object representations. Behavioral studies with primates, which are summarized in this article, support the model of view-based object representations. We designed our computer vision system according to these findings and demonstrate that very precise estimations of the poses of real-world objects are possible even if only a few number of sample views of an object is available. The system can be used for a variety of applications.